DTWNet: a Dynamic Time Warping Network
Xingyu Cai, Tingyang Xu, Jinfeng Yi, Junzhou Huang, Sanguthevar Rajasekaran
Abstract
Dynamic Time Warping (DTW) is widely used as a similarity measure in various domains. Due to its invariance against warping in the time axis, DTW provides more meaningful discrepancy measurements between two signals than other dis- tance measures. In this paper, we propose a novel component in an artificial neural network. In contrast to the previous successful usage of DTW as a loss function, the proposed framework leverages DTW to obtain a better feature extraction. For the first time, the DTW loss is theoretically analyzed, and a stochastic backpropogation scheme is proposed to improve the accuracy and efficiency of the DTW learning. We also demonstrate that the proposed framework can be used as a data analysis tool to perform data decomposition.
BibTeX
@inproceedings{NEURIPS2019_02f063c2,
author = {Cai, Xingyu and Xu, Tingyang and Yi, Jinfeng and Huang, Junzhou and Rajasekaran, Sanguthevar},
booktitle = {Advances in Neural Information Processing Systems},
editor = {H. Wallach and H. Larochelle and A. Beygelzimer and F. d\textquotesingle Alch\'{e}-Buc and E. Fox and R. Garnett},
pages = {},
publisher = {Curran Associates, Inc.},
title = {DTWNet: a Dynamic Time Warping Network},
url = {https://proceedings.neurips.cc/paper_files/paper/2019/file/02f063c236c7eef66324b432b748d15d-Paper.pdf},
volume = {32},
year = {2019}
}